> For the complete documentation index, see [llms.txt](https://docs.chord.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chord.co/get-started/faq.md).

# FAQ

These questions are about [Ask Chord](/analyze-with-ai/ai-chat.md), which lets you ask questions about your data in plain language.

## Data security and privacy

**How does Ask Chord protect my data?**\
Ask Chord follows the same data security and privacy standards as the rest of the Chord platform. Your data never leaves our secure environment unless your team explicitly configures it to.

**Is any of my customer or business data sent to third-party AI providers?**\
No. Ask Chord processes your data within the Chord platform and doesn't send any raw business or customer data to external AI providers.

**Does Ask Chord use my data to train external LLMs?**\
Never. Your data isn't used to train, fine-tune or improve any models outside your organization. Ask Chord uses a multi-LLM architecture that handles different parts of your data separately, so your sensitive data isn't sent to or trained on by public LLMs.

**Can I control what data Ask Chord has access to?**\
Yes. Ask Chord uses only the data a given user is permitted to access. If a user can't view data in Chord, they can't query it with AI either.

## Functionality and capabilities

**What can I use Ask Chord for?**\
You can ask questions about your customers, orders, products and performance. Ask Chord translates these into SQL and returns results from your data.

**What types of questions work best?**\
Clear, specific questions work best. For example:

* "What was our average order value last month?"
* "Which products are most frequently purchased by subscribers?"

**Can I see the SQL behind an answer?**\
Yes. Every response includes the SQL used. Click **View SQL** at the bottom of any answer to view or reuse it.

## Access and use

**Who can use Ask Chord in my organization?**\
Access is permission-based. Reach out to your Chord account team for details on access controls for your organization.

**Do I need special training or technical knowledge?**\
No. Ask Chord is designed for marketers, operators and analysts, and doesn't need any SQL background.

**Who do I contact if something isn't working as expected?**\
Reach out to <help@chord.co> or contact your Chord account team.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.chord.co/get-started/faq.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.